Dynamic energy efficiency management and control system based on AI

Abstract

The invention relates to the technical field of program control, in particular to an AI-based dynamic energy efficiency management and control system, which comprises a data acquisition module based on equipment power and an operation mode, the data acquisition module acquires real-time data of an equipment power sensor, records the change condition of the operation mode, acquires equipment operation state parameters, marks the equipment operation state parameters through timestamps, and transmits the equipment operation state parameters to a server; and arranging according to a time sequence and integrating into a real-time energy consumption data stream. According to the method, by monitoring the equipment power and the operation mode change in real time and calculating the entropy change rate in real time, the system can effectively predict and adapt to the energy consumption change, fine adjustment of the equipment power and optimization of the operation mode are achieved, the energy efficiency can be remarkably improved through the measure, the maximum benefit of energy use is ensured, and the energy utilization efficiency is improved. And a real-time feedback mechanism further enables equipment adjustment measures to be optimized based on actual effects, so that the effectiveness of the adjustment measures is ensured, continuous energy efficiency improvement is supported, and the overall influence on the environment is more positive.

Description

Technical Field

[0001] This invention relates to the field of program control technology, and in particular to an AI-based dynamic energy efficiency management system. Background Technology

[0002] The field of programmable logic controller (PLC) technology involves the use of computer programs to automate the management and regulation of various mechanical or electronic systems. This area primarily focuses on how to optimize system performance, improve efficiency, reduce costs, and prevent malfunctions through pre-programmed procedures or real-time algorithms. PLCs can be applied to a variety of scenarios, including industrial production, environmental management, equipment maintenance, and energy management. These applications encompass not only traditional control systems but also increasingly advanced control strategies based on artificial intelligence and machine learning to achieve more precise and flexible control.

[0003] Dynamic energy efficiency management systems, in particular, utilize advanced programmable control technology to monitor and optimize the energy consumption of equipment or systems in real time. The primary purpose of such systems is to achieve energy conservation and emission reduction by dynamically adjusting and optimizing energy use, while maintaining or improving system performance. Dynamic energy efficiency management systems are commonly found in industrial automation, building energy management, and smart grids. Through real-time data analysis and learning, they continuously adjust operating parameters to adapt to changes in the environment or production needs, thereby achieving efficient energy use.

[0004] Existing technologies often demonstrate insufficient adaptability when dealing with rapidly changing production demands and environmental factors, particularly lacking real-time data analysis and immediate adjustment capabilities when environmental and production needs change rapidly. For example, in highly volatile industrial environments, traditional control systems, due to fixed parameter settings and response delays, cannot adjust equipment states in a timely manner to match the latest operating requirements, leading to low energy efficiency and excessive resource consumption. The sluggish response of such systems not only affects energy utilization efficiency but may also increase equipment wear and tear, shorten equipment lifespan, and pose challenges to maintaining production efficiency and cost control. Summary of the Invention

[0005] The purpose of this invention is to address the shortcomings of existing technologies by proposing an AI-based dynamic energy efficiency management system.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: an AI-based dynamic energy efficiency management system includes:

[0007] The data acquisition module collects real-time data from the device's power sensor based on the device's power and operating mode, records changes in the operating mode, obtains the device's operating status parameters, marks them with timestamps, arranges them in chronological order, and integrates them into a real-time energy consumption data stream.

[0008] The entropy change rate calculation module extracts time series data of equipment power and operation mode based on the real-time energy consumption data stream, analyzes the fluctuation of energy consumption data, calculates the energy consumption difference between adjacent time points, and calculates the entropy change rate of equipment power and operation mode to obtain the dynamic index of entropy change rate.

[0009] The dynamic adjustment strategy module compares the entropy change rate with a set threshold based on the dynamic index of entropy change rate, determines whether the device power output and operating mode need to be adjusted, calculates the required device power adjustment amount, selects the operating mode, adjusts the device power output and operating mode, and generates optimized operating parameters.

[0010] The effect feedback and optimization module uses the optimized operating parameters to adjust the device power output and operating mode, collects the actual energy consumption data after adjustment, compares the actual energy consumption with the expected energy consumption data, calculates the difference between the two, and generates system optimization feedback.

[0011] As a further aspect of the present invention, real-time data from the device's power sensor is collected, and changes in the operating mode are recorded in real time. The changes are marked with timestamps to generate power and operating mode records with timestamps.

[0012] The timestamped power and operating mode records are integrated in chronological order, and data cleaning is performed to remove duplicate and non-logical timestamps, resulting in the processed real-time power and operating mode records.

[0013] The processed real-time power and operating mode records are calculated using the following formula:

[0014]

[0015] Calculate the adjusted energy consumption and generate a real-time energy consumption data stream;

[0016] Among them, P i Δt represents the power at time point i. i It is the time difference between adjacent timestamps. The time difference is represented by 1.2, and E represents the calculated total energy consumption.

[0017] As a further aspect of the present invention, the step of obtaining the entropy change rate dynamic index specifically includes:

[0018] Extract time-series data of device power and operating mode from the real-time energy consumption data stream to reflect the energy consumption of the device at different time points and generate a time-series dataset;

[0019] Based on the time series dataset, the energy consumption difference between each two adjacent points is calculated to reveal the energy consumption fluctuations in the short term and obtain the energy consumption difference sequence.

[0020] Using the aforementioned energy consumption difference sequence, the formula is:

[0021]

[0022] Calculate the entropy change rate of energy consumption differences and generate a dynamic index of entropy change rate;

[0023] Where S represents the entropy rate of change, indicating the uncertainty and variability of energy consumption in a given time series, and p i Represents the energy consumption probability at each time point, log(p i ) is the regular calculation part of information entropy, used to measure the impact of energy consumption contribution at time point i on the total entropy value. α represents the weighting coefficient, used to enhance the sensitivity of the entropy value to extreme fluctuations in energy consumption.

[0024] As a further aspect of the present invention, the step of obtaining the optimized operation parameters specifically includes:

[0025] The entropy change rate dynamic index is compared with a preset threshold to determine whether there is a need to adjust the power output and operating mode. If the entropy change rate exceeds the threshold, it is marked as needing adjustment, and an adjustment need signal is generated.

[0026] Based on the adjustment demand signal, calculate the amount of power that needs to be adjusted, analyze the deviation between the current power and the ideal power, calculate the power adjustment value, and generate power adjustment data;

[0027] Select the appropriate operating mode and apply the power adjustment data using the formula:

[0028] P new =P current +β·ΔP

[0029] Adjust the device power output to the current set value and generate optimized operating parameters;

[0030] Among them, P new P represents the optimized operating parameters. current ΔP represents the current power setting, ΔP represents the calculated power adjustment value, and β is the adjustment coefficient determined based on the equipment performance and response characteristics.

[0031] As a further aspect of the present invention, the step of obtaining the system optimization feedback specifically includes:

[0032] The power output and operating mode of the device are adjusted using the optimized operating parameters to ensure that the device operates according to the current configuration, and the adjusted device status record is generated.

[0033] Based on the adjusted equipment status record, the adjusted actual energy consumption data is collected to ensure that the energy consumption data reflects the operating status of the equipment and to obtain the actual energy consumption data record.

[0034] The actual energy consumption data and expected energy consumption data are retrieved using the following formula:

[0035]

[0036] Calculate the difference between actual energy consumption and expected energy consumption, and generate system optimization feedback;

[0037] Where ΔE represents the energy consumption difference, E actual E represents actual energy consumption data. expected γ represents the expected energy consumption data, γ represents the adjustment coefficient used to balance the effects of relative and absolute differences, and δ represents the smoothing parameter used to reduce the impact of extreme values ​​on the difference calculation.

[0038] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0039] In this invention, by real-time monitoring of equipment power and operating mode changes and real-time calculation of entropy change rate, the system can effectively predict and adapt to energy consumption changes, achieving fine-tuning of equipment power and optimization of operating modes. This measure significantly improves energy efficiency, ensures maximum energy use efficiency, and reduces unnecessary waste. The real-time feedback mechanism further enables equipment adjustment measures to be optimized based on actual results, ensuring the effectiveness of the adjustment measures, supporting continuous energy efficiency improvement, and resulting in a more positive overall environmental impact. Attached Figure Description

[0040] Figure 1 This is a system flowchart of the present invention;

[0041] Figure 2 This is a flowchart of the steps for acquiring real-time energy consumption data stream according to the present invention;

[0042] Figure 3 This is a flowchart illustrating the steps for obtaining the dynamic index of entropy change rate in this invention.

[0043] Figure 4 The flowchart below shows the steps for obtaining optimized operating parameters according to the present invention.

[0044] Figure 5 This is a flowchart of the steps for obtaining system optimization feedback according to the present invention. Detailed Implementation

[0045] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0046] In the description of this invention, it should be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientation or positional relationships, are based on the orientation or positional relationships shown in the accompanying drawings and are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, in the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0047] Example 1

[0048] Please see Figure 1 An AI-based dynamic energy efficiency management system includes:

[0049] The data acquisition module collects real-time data from the device's power sensor based on the device's power and operating mode, records changes in the operating mode, obtains the device's operating status parameters, marks them with timestamps, arranges them in chronological order, and integrates them into a real-time energy consumption data stream.

[0050] The entropy change rate calculation module extracts time series data of equipment power and operation mode based on real-time energy consumption data stream, analyzes the fluctuation of energy consumption data, calculates the energy consumption difference between adjacent time points, and calculates the entropy change rate of equipment power and operation mode to obtain the dynamic index of entropy change rate.

[0051] The dynamic adjustment strategy module compares the entropy change rate with a set threshold based on the dynamic index of entropy change rate, determines whether the equipment power output and operating mode need to be adjusted, calculates the required equipment power adjustment amount, selects the operating mode, adjusts the equipment power output and operating mode, and generates optimized operating parameters.

[0052] The effect feedback and optimization module uses optimized operating parameters to adjust the device's power output and operating mode, collects the actual energy consumption data after adjustment, compares the actual energy consumption with the expected energy consumption data, calculates the difference between the two, and generates system optimization feedback.

[0053] Real-time energy consumption data stream includes equipment power data, operating mode change data, equipment operating status parameters and timestamps; entropy change rate dynamic indicators include equipment power entropy change rate indicators and operating mode entropy change rate indicators; optimized operating parameters include equipment power adjustment parameters and operating mode parameters; system optimization feedback includes energy consumption difference analysis results and optimization effect evaluation.

[0054] Please see Figure 2 The specific steps for obtaining real-time energy consumption data streams are as follows:

[0055] Collect real-time data from the device's power sensor and record each change in operating mode in real time. Use timestamps to mark the changes and generate timestamped power and operating mode records.

[0056] The system collects real-time data from the power sensor of the acquisition device and records each change in operating mode. This process involves configuring the data acquisition hardware and setting up the real-time data processing system. The data is timestamped to ensure the time accuracy of the data. At the same time, each change in operating mode is recorded to ensure that all operating data is captured and correctly correlated with the power reading. Changes are marked with timestamps to generate timestamped power and operating mode records. These records are crucial for data analysis, ensuring the integrity and traceability of the data.

[0057] The power and operating mode records with timestamps are integrated in chronological order, and data cleaning is performed to remove duplicate and non-logical timestamps, resulting in the processed real-time power and operating mode records.

[0058] Using the generated timestamped power and operating mode records, the records are first integrated in chronological order. The integration process involves verifying the data timestamps to exclude records with time errors or discontinuities. Data cleaning includes removing records with duplicate or non-logical timestamps, such as abnormal data caused by equipment failure or data transmission errors. The resulting real-time power and operating mode records provide the basic data for energy consumption calculations, ensuring the accuracy of subsequent calculations and the usability of the data.

[0059] The formula is used to record the processed real-time power and operating mode:

[0060]

[0061] Calculate the adjusted energy consumption and generate a real-time energy consumption data stream;

[0062] Among them, P i Δt represents the power at time point i. i It is the time difference between adjacent timestamps. The time difference is represented by 1.2, and E represents the calculated total energy consumption.

[0063] formula:

[0064]

[0065] The advantage of the formula is that by introducing the 1.2 power of the time period, it enhances the model's sensitivity to power changes over a short period of time, making it suitable for changing operating modes and equipment with large power fluctuations, thus improving the adaptability and accuracy of energy consumption calculation.

[0066] Detailed explanation of the formula and its calculation derivation:

[0067] Set n=5 data points, where P i = [10,15,20,15,10] in kilowatts (kW), corresponding to the time difference Δt i =[1,0.5,0.3,0.5,1] is in hours. Applying the power of 1.2 to each time interval yields...

[0068] The calculation process is as follows:

[0069] E=10·1+15·0.35+20·0.22+15·0.35+10·1

[0070] =10+5.25+4.4+5.25+10=34.9kWh

[0071] The results show that the total energy consumption is 34.9 kWh. This value reflects the total energy consumption of the equipment within a given time period. Based on this model, energy cost budgeting and energy efficiency analysis can be performed more accurately.

[0072] Please see Figure 3 The specific steps for obtaining the dynamic index of entropy change rate are as follows:

[0073] Extract time-series data of device power and operating mode from real-time energy consumption data stream to reflect the energy consumption of devices at different time points and generate time-series datasets;

[0074] When extracting real-time energy consumption data, the first step is to collect data on device power and operating mode based on sensor input. The data comes from the device power sensor and operating mode monitoring system. The real-time power and operating mode changes during each device operation are recorded using a time series method. Timestamps are used to mark the data to ensure that it can be traced back to the time point of each record. Data collection is crucial to ensuring the effectiveness of subsequent analysis. Through the data acquisition module, various operating states of the device are monitored in real time, including power peaks, valleys, and any changes in operating modes. This process involves batch data filtering and preliminary processing, such as removing abnormal data caused by sensor errors or external interference, thus laying a solid foundation for the next step of energy consumption analysis and ensuring that the obtained time series dataset can truly reflect the operating status of the device.

[0075] Based on time series datasets, the energy consumption difference between each pair of adjacent points is calculated to reveal energy consumption fluctuations in the short term and obtain an energy consumption difference sequence.

[0076] After obtaining the time series dataset, the next step is to calculate the energy consumption difference between two adjacent points in the data. This process is completed by performing a difference operation on every two consecutive data points. The purpose is to reveal the fluctuation of equipment energy consumption in the short term. Fluctuation analysis is a key indicator for evaluating the stability of equipment performance and helps engineers analyze the energy consumption performance of equipment under different operating modes. In addition, by comparing the energy consumption differences at different time points, signs of equipment failure or performance degradation can be identified. This analysis process not only includes numerical calculations but also involves data visualization, which makes it easier for technicians to monitor the trend of energy consumption fluctuations. By setting thresholds, energy consumption fluctuations that exceed the normal range can be automatically identified, thereby triggering alarms or prompts and providing decision support for equipment maintenance.

[0077] Using the energy consumption difference sequence, the formula is:

[0078]

[0079] Calculate the entropy change rate of energy consumption differences and generate a dynamic index of entropy change rate;

[0080] Where S represents the entropy rate of change, indicating the uncertainty and variability of energy consumption in a given time series, and p i Represents the energy consumption probability at each time point, log(p i ) is the regular calculation part of information entropy, used to measure the impact of energy consumption contribution at time point i on the total entropy value. α represents the weighting coefficient, used to enhance the sensitivity of the entropy value to extreme fluctuations in energy consumption.

[0081] formula:

[0082]

[0083] The advantage of the formula is that by introducing the energy consumption ratio and adjustment coefficient, it can measure and analyze the entropy change rate of energy consumption fluctuations and its performance under extreme changes, which helps to dynamically evaluate the energy efficiency performance of equipment.

[0084] Detailed explanation of the formula and its calculation derivation:

[0085] The total energy consumption of the equipment is set to 10,000 kWh within a monitoring period. The energy consumption at five recorded time points is 2,000, 2,500, 1,500, 3,000, and 1,000 kWh, respectively. First, calculate the percentage p of energy consumption at each time point. i For example, the first time point

[0086] Then, substituting into the formula, we calculate the entropy contribution of each point. Assuming α = 0.5, the entropy contribution of the first point is -0.2 × (log(0.2) + 0.5 × 0.2). 2)≈0.136. The total entropy change rate S is obtained by summing the entropy contributions of all points.

[0087] The results show that by comprehensively referencing the energy consumption ratio and energy consumption fluctuation, a quantified entropy change rate can be obtained, providing a scientific basis for iteratively optimizing equipment operating parameters and improving energy efficiency.

[0088] Please see Figure 4 The specific steps for obtaining optimized operation parameters are as follows:

[0089] Compare the dynamic index of entropy change rate with the preset threshold to determine whether there is a need to adjust the power output and operating mode. If the entropy change rate exceeds the threshold, it is marked as needing adjustment, and an adjustment demand signal is generated.

[0090] The process of comparing the entropy change rate with a preset threshold involves real-time monitoring of the device's power output and operating mode. After real-time data acquisition, it is processed by a data analysis system to obtain the real-time value of the entropy change rate. This value is then compared with a preset threshold. The entropy change rate is obtained by collecting the device's operating data and using statistical methods. After comparison with the preset threshold, the system automatically determines whether the threshold is exceeded. If it is exceeded, an adjustment signal is triggered. This process ensures that the device operates in the optimal state, improves energy efficiency, and guarantees device safety.

[0091] Based on the adjustment demand signal, calculate the amount of power that needs to be adjusted, analyze the deviation between the current power and the ideal power, calculate the power adjustment value, and generate power adjustment data;

[0092] Based on the adjustment demand signal, the system automatically calculates the required power adjustment amount. This involves calculating the deviation between the current power setting and the target power, acquiring real-time power data through the data acquisition system, comparing it with the set target power, and processing the difference data through an algorithm to generate an adjustment value. This value indicates how much power to increase or decrease to achieve the ideal state. During the adjustment process, the system will continuously monitor and adjust until the preset target power is reached, ensuring the efficient operation of the equipment.

[0093] Select the appropriate operating mode and apply the power adjustment data using the formula:

[0094] P new =P current +β·ΔP

[0095] Adjust the device power output to the current set value and generate optimized operating parameters;

[0096] Among them, P new P represents the optimized operating parameters. current ΔP represents the current power setting, ΔP represents the calculated power adjustment value, and β is the adjustment coefficient determined based on the equipment performance and response characteristics.

[0097] formula:

[0098] P new =P current +β·ΔP

[0099] The advantage of the formula is that it provides a method to directly adjust the power of the equipment to the ideal state. By adjusting the coefficient β, the adjustment range can be flexibly controlled to match the characteristics and operational requirements of different equipment.

[0100] Detailed explanation of the formula and its calculation derivation:

[0101] Set the current power P current The power required to be adjusted is ΔP = 50kW, and the adjustment coefficient β is set to 0.8. Substitute these values ​​into the formula for calculation:

[0102] P new =500 + 0.8·50

[0103] P new =500+40

[0104] P new =540kW

[0105] The results show that the adjusted new power setting is 540kW, which means that the power output of the equipment will increase to match the changes in workload and ensure the continuity and stability of equipment operation.

[0106] Please see Figure 5 The specific steps for obtaining system optimization feedback are as follows:

[0107] By optimizing operating parameters, the power output and operating mode of the equipment are adjusted to ensure that the equipment operates according to the current configuration, and the adjusted equipment status record is generated.

[0108] Adjusting the power output and operating mode of the equipment ensures that it operates according to the current configuration. This step involves evaluating the existing settings of the equipment and adjusting the equipment status based on optimized parameters. It is essential to ensure that all adjustments are directly applied to the equipment control system. These adjustments should be based on actual operating data and preset performance targets. The adjusted equipment status is automatically recorded by a real-time monitoring system to ensure the accuracy and real-time updates of the recorded data. This is crucial for subsequent performance evaluation and energy consumption optimization.

[0109] Based on the adjusted equipment status records, the adjusted actual energy consumption data is collected to ensure that the energy consumption data reflects the operating status of the equipment and to obtain the actual energy consumption data records.

[0110] Collect adjusted actual energy consumption data. The data can intuitively reflect the operating efficiency of the equipment after adjustment. Data collection should be completed through sensors and data acquisition systems. The system must be calibrated regularly to ensure the accuracy of the data. The actual energy consumption data record should include not only the total power consumption, but also the time distribution and peak information of power consumption. These data are crucial for comparing actual energy consumption and expected energy consumption and can directly affect the accuracy of energy consumption difference analysis.

[0111] To retrieve actual energy consumption data records and expected energy consumption data, use the following formula:

[0112]

[0113] Calculate the difference between actual energy consumption and expected energy consumption, and generate system optimization feedback;

[0114] Where ΔE represents the energy consumption difference, E actual E represents actual energy consumption data. expected γ represents the expected energy consumption data, γ represents the adjustment coefficient used to balance the effects of relative and absolute differences, and δ represents the smoothing parameter used to reduce the impact of extreme values ​​on the difference calculation.

[0115] formula:

[0116]

[0117] The advantages of the formula are that it not only calculates the absolute difference in energy consumption, but also increases the flexibility and accuracy of the calculation by introducing the adjustment coefficient γ and the smoothing parameter δ, making it more adaptable to different operating conditions and environmental changes, and helping to accurately evaluate the effectiveness of adjustment measures.

[0118] Detailed explanation of the formula and its calculation derivation:

[0119] Setting E actual =150kWh, E expected =145kWh, γ=0.05, δ=1.5, then:

[0120]

[0121] The results show that there is a difference of 5.02666 kWh between the adjusted actual energy consumption and the expected energy consumption, indicating that the adjustment measures have achieved the expected results, but there is still room for iterative optimization.

[0122] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention in any other way. Any person skilled in the art may make changes or modifications to the above-disclosed technical content to create equivalent embodiments that can be applied to other fields. However, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the protection scope of the present invention.

Claims

1. A dynamic energy efficiency management and control system based on AI, characterized in that: The system comprises: The data acquisition module collects real-time data from the device power sensor based on the device power and operation mode, records changes in the operation mode, obtains device operating status parameters, marks them with timestamps, arranges them in chronological order, and integrates them into a real-time energy consumption data stream; The entropy change rate calculation module extracts the time series data of the device power and the operation mode based on the real-time energy consumption data stream, analyzes the fluctuation degree of the energy consumption data, calculates the energy consumption difference at adjacent time points, and calculates the entropy change rate of the device power and the operation mode to obtain the entropy change rate dynamic index; The dynamic adjustment strategy module compares the entropy change rate with the set threshold value according to the entropy change rate dynamic indicator, determines whether the device power output and the operation mode need to be adjusted, calculates the required device power adjustment amount, selects the operation mode, adjusts the device power output and the operation mode, and generates optimized operation parameters; The effect feedback and optimization module uses the optimized operating parameters to adjust the equipment power output and operating mode, collects the adjusted actual energy consumption data, compares the actual energy consumption with the expected energy consumption data, calculates the difference between the two, and generates system optimization feedback.

2. The AI-based dynamic energy efficiency management and control system according to claim 1, characterized in that: Collect real-time data from the device power sensor and record each change in operation mode in real time, mark the change with a timestamp, and generate a timestamped record of power and operation mode; Using the power and operation mode records with timestamps, integrating them in chronological order, and performing data cleaning to remove duplicate and non-logical timestamps, to obtain sorted real-time power and operation mode records; For the collated real-time power and operation mode records, the formula is used: Calculate the adjusted energy consumption and generate real-time energy consumption data stream; Among them, P i represents the power at the i-th time point, Δt i is the time difference between adjacent timestamps, represents the 1.2th power of the time difference, and E represents the calculated total energy consumption.

3. The AI-based dynamic energy efficiency management and control system according to claim 2 is characterized in that: The steps for obtaining the entropy change rate dynamic index are specifically as follows: Extracting time series data of device power and operation mode from the real-time energy consumption data stream to reflect the energy consumption of the device at differentiated time points and generate a time series data set; Based on the time series data set, the energy consumption difference between each two adjacent points is calculated to reveal the energy consumption fluctuation in the short term and obtain the energy consumption difference sequence; Using the energy consumption difference sequence, the formula is adopted: Calculate the entropy change rate of energy consumption difference and generate a dynamic index of entropy change rate; Among them, S represents the entropy change rate, which indicates the uncertainty and variability of energy consumption in a given time series, and p i represents the energy consumption probability at each time point, log(p i ) is the conventional calculation part of information entropy, which is used to measure the impact of energy consumption contribution at the i-th time point on the total entropy value. α represents the weight coefficient, which is used to enhance the sensitivity of entropy value to extreme fluctuations in energy consumption.

4. The AI-based dynamic energy efficiency management and control system according to claim 3 is characterized in that: The steps of obtaining the optimization operation parameters are specifically as follows: Comparing the entropy change rate dynamic index with a preset threshold value to determine whether there is a need to adjust the power output and the operation mode, if the entropy change rate exceeds the threshold value, it is marked as requiring adjustment, and an adjustment demand signal is generated; According to the adjustment demand signal, the amount of power to be adjusted is calculated, the deviation between the current power and the ideal power is analyzed, the power adjustment value is calculated, and the power adjustment data is generated; Select the appropriate operating mode and apply the power adjustment data using the formula: P new =P current +β·ΔP Adjust the equipment power output to the current set value and generate optimized operating parameters; Among them, P new represents the optimized operating parameters, P current represents the current power setting, ΔP represents the calculated power adjustment value, and β is the adjustment coefficient determined based on the equipment performance and response characteristics.

5. The AI-based dynamic energy efficiency management and control system according to claim 4 is characterized in that: The steps for obtaining the system optimization feedback are specifically as follows: Using the optimized operating parameters, adjusting the power output and operating mode of the device to ensure that the device operates according to the current configuration, and recording and generating a record of the adjusted device status; Based on the adjusted equipment status record, collect the adjusted actual energy consumption data to ensure that the energy consumption data reflects the operating status of the equipment and obtain the actual energy consumption data record; The actual energy consumption data record and the expected energy consumption data are called, and the formula is used: Calculate the difference between actual and expected energy consumption and generate system optimization feedback; Among them, ΔE represents the difference in energy consumption, E actual Represents actual energy consumption data, E expected represents the expected energy consumption data, γ represents the adjustment coefficient, which is used to balance the impact of relative differences and absolute differences, and δ represents the smoothing parameter, which is used to reduce the impact of extreme values ​​on the difference calculation.

Images